Trine Jul Larsen, Maria Bråthen Pettersen, Helena Nygaard Jensen, Michael Lynge Pedersen, Henrik Lund-Andersen, Marit Eika Jørgensen, Stine Byberg
{"title":"The use of artificial intelligence to assess diabetic eye disease among the Greenlandic population.","authors":"Trine Jul Larsen, Maria Bråthen Pettersen, Helena Nygaard Jensen, Michael Lynge Pedersen, Henrik Lund-Andersen, Marit Eika Jørgensen, Stine Byberg","doi":"10.1080/22423982.2024.2314802","DOIUrl":null,"url":null,"abstract":"<p><p><b>Background:</b> Retina fundus images conducted in Greenland are telemedically assessed for diabetic retinopathy by ophthalmological nurses in Denmark. Applying an AI grading solution, in a Greenlandic setting, could potentially improve the efficiency and cost-effectiveness of DR screening.<b>Method:</b> We developed an AI model using retina fundus photos, performed on persons registered with diabetes in Greenland and Denmark, using Optos® ultra wide-field scanning laser ophthalmoscope, graded according to ICDR.Using the ResNet50 network we compared the model's ability to distinguish between different images of ICDR severity levels in a confusion matrix.<b>Results:</b> Comparing images with ICDR level 0 to images of ICDR level 4 resulted in an accuracy of 0.9655, AUC of 0.9905, sensitivity and specificity of 96.6%.Comparing ICDR levels 0,1,2 with ICDR levels 3,4, we achieved a performance with an accuracy of 0.8077, an AUC of 0.8728, a sensitivity of 84.6% and a specificity of 78.8%. For the other comparisons, we achieved a modest performance.<b>Conclusion:</b> We developed an AI model using Greenlandic data, to automatically detect DR on Optos retina fundus images. The sensitivity and specificity were too low for our model to be applied directly in a clinical setting, thus optimising the model should be prioritised.</p>","PeriodicalId":13930,"journal":{"name":"International Journal of Circumpolar Health","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10877649/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Circumpolar Health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/22423982.2024.2314802","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/15 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Retina fundus images conducted in Greenland are telemedically assessed for diabetic retinopathy by ophthalmological nurses in Denmark. Applying an AI grading solution, in a Greenlandic setting, could potentially improve the efficiency and cost-effectiveness of DR screening.Method: We developed an AI model using retina fundus photos, performed on persons registered with diabetes in Greenland and Denmark, using Optos® ultra wide-field scanning laser ophthalmoscope, graded according to ICDR.Using the ResNet50 network we compared the model's ability to distinguish between different images of ICDR severity levels in a confusion matrix.Results: Comparing images with ICDR level 0 to images of ICDR level 4 resulted in an accuracy of 0.9655, AUC of 0.9905, sensitivity and specificity of 96.6%.Comparing ICDR levels 0,1,2 with ICDR levels 3,4, we achieved a performance with an accuracy of 0.8077, an AUC of 0.8728, a sensitivity of 84.6% and a specificity of 78.8%. For the other comparisons, we achieved a modest performance.Conclusion: We developed an AI model using Greenlandic data, to automatically detect DR on Optos retina fundus images. The sensitivity and specificity were too low for our model to be applied directly in a clinical setting, thus optimising the model should be prioritised.
期刊介绍:
The International Journal of Circumpolar Health is published by Taylor & Francis on behalf of the Circumpolar Health Research Network [CircHNet]. The journal follows the tradition initiated by its predecessor, Arctic Medical Research. The journal specializes in circumpolar health. It provides a forum for many disciplines, including the biomedical sciences, social sciences, and humanities as they relate to human health in high latitude environments. The journal has a particular interest in the health of indigenous peoples. It is a vehicle for dissemination and exchange of knowledge among researchers, policy makers, practitioners, and those they serve.
International Journal of Circumpolar Health welcomes Original Research Articles, Review Articles, Short Communications, Book Reviews, Dissertation Summaries, History and Biography, Clinical Case Reports, Public Health Practice, Conference and Workshop Reports, and Letters to the Editor.